I have transformed the data by relative abundance. I am plotting only the most abundance phyla and the composition of the phyla.
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 1.1898, num df = 13, denom df = 13, p-value = 0.7587
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.3819612 3.7063408
## sample estimates:
## ratio of variances
## 1.189823
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 1.2424, num df = 13, denom df = 13, p-value = 0.7014
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.3988259 3.8699859
## sample estimates:
## ratio of variances
## 1.242357
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 0.60575, num df = 13, denom df = 13, p-value = 0.3778
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.1944614 1.8869458
## sample estimates:
## ratio of variances
## 0.6057541
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 0.39285, num df = 13, denom df = 13, p-value = 0.1043
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.1261126 1.2237268
## sample estimates:
## ratio of variances
## 0.3928452
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 9.3538, num df = 13, denom df = 13, p-value = 0.0002779
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 3.002786 29.137372
## sample estimates:
## ratio of variances
## 9.353784
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 4.3167, num df = 13, denom df = 13, p-value = 0.01295
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 1.385753 13.446581
## sample estimates:
## ratio of variances
## 4.31667
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 0.35141, num df = 13, denom df = 13, p-value = 0.07021
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.1128096 1.0946421
## sample estimates:
## ratio of variances
## 0.3514059
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 2.1902, num df = 13, denom df = 13, p-value = 0.1708
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.7031007 6.8225006
## sample estimates:
## ratio of variances
## 2.190184
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 0.19041, num df = 13, denom df = 13, p-value = 0.005274
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.0611274 0.5931465
## sample estimates:
## ratio of variances
## 0.190414
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 0.14914, num df = 13, denom df = 13, p-value = 0.001594
## alternative hypothesis: true ratio of variances is not equal to 1
## 95 percent confidence interval:
## 0.04787843 0.46458586
## sample estimates:
## ratio of variances
## 0.149143
## png
## 2
## png
## 2
## png
## 2
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 2.0686, num df = 13, denom df = 13, p-value = 0.1017
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 0.8027428 Inf
## sample estimates:
## ratio of variances
## 2.06861
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 3.6258, num df = 13, denom df = 13, p-value = 0.01365
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 1.407019 Inf
## sample estimates:
## ratio of variances
## 3.625785
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 9.9177, num df = 13, denom df = 13, p-value = 0.000101
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 3.848648 Inf
## sample estimates:
## ratio of variances
## 9.917684
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 1.9709, num df = 13, denom df = 13, p-value = 0.1172
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 0.7648359 Inf
## sample estimates:
## ratio of variances
## 1.970926
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 5.6892, num df = 13, denom df = 13, p-value = 0.001798
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 2.207744 Inf
## sample estimates:
## ratio of variances
## 5.689196
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 13.079, num df = 13, denom df = 13, p-value = 2.147e-05
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 5.075521 Inf
## sample estimates:
## ratio of variances
## 13.07925
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 11.266, num df = 13, denom df = 13, p-value = 4.987e-05
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 4.372062 Inf
## sample estimates:
## ratio of variances
## 11.26648
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 2.8814, num df = 13, denom df = 13, p-value = 0.03353
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 1.118151 Inf
## sample estimates:
## ratio of variances
## 2.881395
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 1.0994, num df = 13, denom df = 13, p-value = 0.4334
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 0.4266429 Inf
## sample estimates:
## ratio of variances
## 1.099428
##
##
## F test to compare two variances
##
## data: c[, i] and w[, i]
## F = 4.6949, num df = 13, denom df = 13, p-value = 0.004438
## alternative hypothesis: true ratio of variances is greater than 1
## 95 percent confidence interval:
## 1.821902 Inf
## sample estimates:
## ratio of variances
## 4.694907
##
## Welch Two Sample t-test
##
## data: a and b
## t = 2.3163, df = 11.473, p-value = 0.01997
## alternative hypothesis: true difference in means is greater than 0
## 95 percent confidence interval:
## 0.003095143 Inf
## sample estimates:
## mean of x mean of y
## 0.018179730 0.004579922
Now I think it might be interesting to look at these plots excluding all actinobacteria, proteobacteria, and bacteroides (The vast majority of taxa belong to those phyla)